Created
February 12, 2019 15:06
-
-
Save remoharsono/b170ea8232b27318e07f59b84dc1d43e to your computer and use it in GitHub Desktop.
List your twitter followers
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup | |
headers = { | |
'User-Agent': 'Mozilla/5.0 (Linux; Android 4.0.4; Galaxy Nexus Build/IMM76B) AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.133 Mobile Safari/535.19', | |
} | |
def get_next(url, start_number, num_pages, page_number): | |
response = requests.get(url, headers=headers) | |
soup = BeautifulSoup(response.text, 'html.parser') | |
user_list = soup.find('div', attrs={'class':'user-list'}) | |
user_items = user_list.find_all('table', attrs={'class':'user-item'}) | |
row_number = start_number | |
for user_item in user_items: | |
info = user_item.find('td', attrs={'class':'info'}) | |
anchors = info.find_all('a', attrs={'href':False}) | |
for anchor in anchors: | |
print(str(row_number) + " " + anchor['name']) | |
row_number += 1 | |
more = soup.find('div', attrs={'class':'w-button-more'}) | |
if more is not None: | |
more_anchor = more.find('a') | |
next_segment = more_anchor['href'] | |
page_number += 1 | |
if page_number < num_pages: | |
url = base_url + next_segment | |
get_next(url, row_number, num_pages, current_page) | |
base_url = 'https://mobile.twitter.com' | |
username = 'remoharsono' | |
url = base_url + '/' + username + '/followers' | |
response = requests.get(url, headers=headers) | |
soup = BeautifulSoup(response.text, 'html.parser') | |
num_followers = soup.find('span', attrs={'class':'count'}) | |
followers_per_page = 20 | |
num_pages = (int(num_followers.text) + int(followers_per_page) - 1) / int(followers_per_page) | |
num_pages = int(num_pages) | |
print("Number of followers: " + num_followers.text) | |
print("Number of followers per page: " + str(followers_per_page)) | |
print("Number of pages: " + str(num_pages)) | |
user_list = soup.find('div', attrs={'class':'user-list'}) | |
user_items = user_list.find_all('table', attrs={'class':'user-item'}) | |
row_number = 1 | |
for user_item in user_items: | |
info = user_item.find('td', attrs={'class':'info'}) | |
anchors = info.find_all('a', attrs={'href':False}) | |
for anchor in anchors: | |
print(str(row_number) + " " + anchor['name']) | |
row_number += 1 | |
more = soup.find('div', attrs={'class':'w-button-more'}) | |
more_anchor = more.find('a') | |
next_segment = more_anchor['href'] | |
# sample segment: /wokwith/followers?cursor=1624052730914607304 | |
current_page = 1 | |
url = base_url + next_segment | |
get_next(url, row_number, num_pages, current_page) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment